US9836882B2 - Systems and methods for rapid three-dimensional modeling with real facade texture - Google Patents

Abstract

A computer system is described for automatically generating a 3D model, including hardware and non-transitory computer readable medium accessible by the hardware and storing instructions that when executed by the hardware cause it to obtain wire-frame data of a structure within a geographic area; identify a geographic location of the structure; retrieve multiple geo-referenced oblique images representing the geographic location and containing a real façade texture of the structure; locate a geographical position of a real façade texture of the structure; select one or more base oblique image from the multiple oblique images by analyzing, with selection logic, image raster content of the real façade texture depicted in the multiple oblique images, and, apply the real façade texture of the one or more base oblique image to the wire-frame data of the structure to create a three dimensional model providing a real-life representation of physical characteristics of the structure.

Description

INCORPORATION BY REFERENCE OF RELATED APPLICATIONS

The present patent application is a continuation of U.S. Ser. No. 15/056,598 filed Feb. 29, 2016, which is a continuation of U.S. Ser. No. 14/633,285 filed Feb. 27, 2015, issued Mar. 1, 2016, as U.S. Pat. No. 9,275,496, which is a continuation of U.S. Ser. No. 14/152,638, filed Jan. 10, 2014, issued Mar. 3, 2015, as U.S. Pat. No. 8,970,615, which is a continuation of U.S. Ser. No. 13/903,683, filed May 28, 2013, issued Feb. 11, 2014, as U.S. Pat. No. 8,648,872, which is a continuation of U.S. Ser. No. 11/998,974, filed Dec. 3, 2007, issued Sep. 10, 2013, as U.S. Pat. No. 8,531,472, the entire contents of all of which are hereby incorporated herein by reference in their entirety.

STATEMENT REGARDING FEDERALLY SPONSORED RESEARCH OR DEVELOPMENT

Not Applicable.

THE NAMES OF THE PARTIES TO A JOINT RESEARCH AGREEMENT

Not Applicable.

REFERENCE TO A “SEQUENCE LISTING,” A TABLE, OR A COMPUTER PROGRAM LISTING APPENDIX SUBMITTED ON A COMPACT DISC AND AN INCORPORATION-BY-REFERENCE OF THE MATERIAL ON THE COMPACT DISC (SEE §1.52(E)(5))

Not Applicable.

BACKGROUND OF THE INVENTION

Technology advancements within the three-dimensional modeling industry are providing avenues for physical simulation of real-life and hypothetical situations on computer systems. These models can provide valuable information for strategic and tactical planning. For example, three-dimensional models of city streets can provide first responders information regarding current city developments including entryway locations, building recognition, and the like. This information is valuable in reducing response time during emergency conditions. Further, emergency personal can train for emergency situations through simulated scenarios provided by or with the three-dimensional models.

Currently within the art, oblique images obtained from aerial photographs are used to provide close-to-accurate representations of each building's surface within the three-dimensional model. However, generally, it is difficult to obtain these oblique images with unobstructed views of the building's surface. For instance, most buildings in downtown regions of a major metropolitan city are close in proximity to one another. It becomes burdensome and time consuming to capture aerial images of each building without an obstruction, such as a neighboring building. Further, finding a single image without obstructions from the thousands of aerial images obtained, would be extremely time consuming and cost-prohibitive and may require three-dimensional modeling of all obstructing structures.

Some three-dimensional models edit the obstructed portion of the oblique image by approximating the building's surface using other portions of the same building. Although this method does provide a representation of the building within the three-dimensional model, the representation goes on the assumption that all portions of the building are created equal. However, this assumption is problematic as an obstructed area may have uniquely placed doorways and/or windows that may be ignored by the approximation.

Alternatively, a user can manually manipulate two or more oblique images to form a single image having an unobstructed view of the façade. This type of manual manipulation is slow and tedious, and requires experience and expertise in the modeling field.

BRIEF SUMMARY OF THE INVENTION

In one embodiment, the present invention is related to a method of automatically generating a three-dimensional model of a structure. The three-dimensional model of the structure preferably includes real façade textures obtained from geo-referenced oblique images. The geographical position of the real façade texture is provided using wire-frame data. A base oblique image is selected from geo-referenced oblique images using the geographical positions obtained from the wire-frame data. The base oblique image is selected from the geo-referenced oblique images based on analysis of the image raster content of the real façade texture, and the real façade texture of the base oblique image is then applied to the three-dimensional model.

In one version, the real façade texture is analyzed to locate at least one occlusion. Occlusions can include obstructions in the view of the real façade texture such as an overlapping building, image distortions within the base oblique images, and/or the like. Occlusions may be located using pattern recognition, contrast, and/or the like. Unoccluded image characteristics of the real façade texture are provided by at least one geo-referenced oblique image. The unoccluded image characteristics of the occlusion are applied to the real façade texture to form a mosaic image.

In another version, the real façade texture is analyzed and corrected for misalignment. Misalignment may be corrected by shrinking and/or stretching the real façade texture, extracting portions of the real façade texture, and/or the like. For example, the outer boundaries of the real façade texture may be extracted using discontinuities in depth, discontinuities in surface orientation, variations in scene illumination, and/or the like.

In another version, the wire-frame data of the three-dimensional model is analyzed to locate the geographical position of a roof of the structure. Images containing the roof are provided and a base image is selected and applied to the three-dimensional model. The images may be nadir images or oblique images. Selection of the base image is based on the image raster content, for example, a base image may be preferred in which the image raster content contains a greater proportion of pixels associated with the roof as compared with other base images.

In another embodiment, the present invention is related to a method of automatically generating a three-dimensional model having structures with real façade textures. The real façade textures are obtained from geo-referenced aerial oblique images. Wire-frame data is analyzed to locate geographical positions of the real façade textures of the structures within a geographical area. An oblique image showing the real façade texture is selected. Where present, at least one incorrect area within at least a portion of the real façade texture may be identified. The incorrect area within the portion of the real façade texture is automatically corrected.

BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWING

So the above-recited features and advantages of the present invention may be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments thereof that are illustrated in the appended drawings. It is to be noted, however, that the appended drawings illustrate only typical embodiments of this invention and are therefore not to be considered limiting in scope, for the invention may admit to other equally-effective embodiments.

FIG. 1 is a block diagram of one embodiment of the rapid three-dimensional modeler system having real-façade textures obtained from geo-referenced images in accordance with the present invention.

FIG. 2 is a pictorial representation of a three-dimensional model having real façade textures.

FIG. 3 is a pictorial representation of wire-frame data providing a geographical position of a real façade texture of a structure.

FIG. 4 is a pictorial representation of terrain data providing a geographical position of a real façade texture of a structure.

FIG. 5 is a pictorial representation of an exemplary oblique image obtained from an aerial camera, the oblique image displaying a real façade texture of a structure.

FIG. 6 is an exemplary function flow chart of a method for generating a three-dimensional model of a structure including real façade textures obtained from geo-referenced images.

FIG. 7 is a schematic block diagram of the formation of a mosaic image from a base image and a geo-referenced image including an unoccluded image characteristic.

FIG. 8 is a schematic block diagram of the formation of a mosaic image from a base image and a geo-referenced image including an unoccluded image characteristic, the base image and the geo-referenced image having different views.

FIG. 9 is a schematic diagram of an exemplary embodiment of a system for providing three-dimensional models having real façade textures in accordance with the present invention.

DETAILED DESCRIPTION OF EXEMPLARY EMBODIMENTS

Embodiments of the invention are shown in the above-identified Figures and described in detail below. In describing the embodiments, like or identical reference numerals are used to identify common or similar elements. The Figures are not necessarily to scale and certain features and certain views of the Figures may be shown exaggerated in scale or in schematic in the interest of clarity and conciseness.

Referring now to the drawings and in particular toFIGS. 1 and 2, shown therein and designated by areference numeral10 is an exemplary system for rapidly creating a three-dimensional model12 of astructure14 includingreal façade textures16. Thesystem10 providesreal façade textures16 obtained from geo-referencedimages18. The three-dimensional model12, including thereal façade textures16, provides an accurate representation of a geographic area. An exemplary three-dimensional model12 is shown inFIG. 2 and preferably includes structures such as buildings, thoroughfares, and other associated fixtures. Such features provide real-life representation of the geographical area useful in strategic planning, tactical planning, tactical debriefing, simulation, real-time simulation, first response actions, engineering designs, and/or the like. Although the geographic area applies to physical characteristics of an area, it is not limited to the topographical features of the Earth's surface. For example, the system and methods described herein may apply to rapid three-dimensional modeling techniques for medical imaging.

Generally, thesystem10 identifies ageographical position22 of at least onereal façade texture16 of thestructure14. Thesystem10 locates geo-referencedimages18 containing thereal façade texture16 and selects a base image19 (SeeFIG. 7) having optimal image characteristics of thereal façade texture16. Thisbase image19 provides at least one real façade texture applied to thestructure14 forming the three-dimensional model12.

Thesystem10 identifies thegeographical position22 of thereal façade textures16 within the geo-referencedimages18. In one embodiment, thesystem10 uses wire-frame data20 of thestructure14 to provide thegeographical position22 through the identification of boundaries (17a,17b,17c,17d. . . ) of thereal façade texture16, as best illustrated inFIG. 3. Although the wire-frame data20 ofFIG. 3 illustrates boundaries17a-17dof thereal façade texture16 as a rectangle, it will be appreciated by one skilled in the art, the boundaries17a-17dmay comprise a circle, square, triangle, or any fanciful shape. Alternatively, an edge-detection algorithm may be used to locate thegeographical position22 of thereal façade texture16 within the wire-frame data. Preferably, wire-frame data20 is obtained from publicly available information of buildings, structures, elevations and the like. For example, publicly available wire-frame data20 commonly stored as *.shp files may be used. Alternatively, wire-frame data20 of thestructure14 may be created based on the particular application of the present invention using techniques commonly known within the art.

Thesystem10 may also useterrain data24 to provide thegeographical position22 of thereal façade texture16. For example, the system may identify boundaries (17a,17b,17c,17d. . . ) of thereal façade texture16 as illustrated inFIG. 4. AlthoughFIG. 4 illustrates boundaries17a-17dof thereal façade texture16 as a rectangle, it will be appreciated by one skilled in the art, the boundaries17a-17dmay comprise a circle, square, triangle, or any fanciful shape. Alternatively, an edge-detection algorithm may be used to locate thegeographical position22 of thereal façade texture16 within theterrain data24. Terrain data may include Digital Terrain Models (DTMs), Digital Elevation Models (DEMs), and/or the like. Generally,terrain data24 is comprised of sets of universal terrain map coordinates identifying location and elevation of geographical regions. The coordinate system may be any coordinate system including latitude and longitude or any other geographical coordinate system suitable for use with the present invention. Preferably, theterrain data24 is a publicly available Digital Terrain Model. Alternatively,terrain data24 for a geographical area may be extracted or created from publicly available contour images, and/or may be created for the specific application intended.

The geo-referencedimage18 providing thereal façade texture16, as illustrated inFIG. 5, may use any color space and be stored in any industry supported file format, such as TIFF, JPEG, GIF, BMP, ECW, and/or the like. Additionally, the geo-referenced images preferably contain or are referenced to or coordinated with information regarding the location and orientation of the camera, focal length, the physical size of the sensor, and/or the like.

The geo-referencedimages18 are preferably nadir images and/or oblique images. Nadir images, as described herein, provide vertical or orthogonal views of the geographic area. Nadir images may be an image captured from an overhead position, a position above thestructure14, or at a right angle or an angle near to a right angle to thestructure14. For example, the image may be taken from an overhead position as related to thestructure14 at an eighty-seven degree angle or similar angle close to a ninety-degree angle. A nadir image may be rectified to fit an associated wire-frame, DTM, DEM, and/or the like. Rectifying a nadir image may entail mapping the pixels to the coordinates of the wire-frame, DTM, DEM, and/or the like.

As nadir images typically do not express the details and characteristics of structures and objects, in the currently preferred embodiment, oblique images will typically, but not exclusively, be used for the purposes of the present invention. Oblique images, as described herein, are images taken at an angle other than that of the nadir perspective or images derived from the nadir perspective. Oblique images provide a perspective line of sight that generally reveals information not visible from an orthogonal or orthophoto view. For example, an oblique image may have an angle to thestructure14 in the range of about zero degrees to about eighty-nine degrees.

Referring toFIGS. 1 and 6, thefirst step50 in generating a three-dimensional model havingreal façade textures16 is to obtain a relevant geographic location of thestructure14. Once the geographic location is determined, a set of geo-referencedimages18 representing the location are obtained, which is thesecond step52. The geo-referencedimages18 may be obtained as discussed above or in any other suitable fashion. The relevantgeographical location22 may be determined internally, calculating a position based upon a mathematical formula, or through an external entity, for example, by a database or user. Preferably, a user indicates an initial geographic location, for example, such that subsequent locations may be mathematically calculated using image boundaries.

Thethird step54 is to locate thegeographical position22 of at least onereal façade texture16 of thestructure14. Wire-frame data20 and/orterrain data24 may be used to locate thegeographical position22 coordinating to thestructure14 as previously discussed herein.

Thefourth step56 is to select abase image19 containing thereal façade texture16 from the geo-referencedimages18. Thebase image19 is preferably selected as one that accurately represents thereal façade texture16 and may be automatically selected by thesystem10 or selected or determined by the user from a limited selection of geo-referencedimages18 provided by thesystem10.

Thebase image19 containing thereal façade texture16 is selected from the geo-referencedimages18 of thestructure14 based upon a factorial analysis of the image raster content of each geo-referencedimage18 of thestructure14. The factorial analysis may include a weighted determination based on the resolution of the image, colour depth of the image, proportional size of the real façade texture, contrast, time of day the image was captured, time of year the image was captured and/or the like. Foliage may also play a role in the factorial analysis. For example, thebase image19 may be selected based on the contrast in lighting conditions. Contrast may be measured as a histogram and provide information regarding shadows within the image. Such information is relevant in constructing replications of large geographical areas, as the three-dimensional model12 would generally includereal façade textures16 representing the same approximate time of day and/or time of year.

The fifth step is to apply or relate thereal façade texture16 of thebase image19 to the three-dimensional model12. The three-dimensional model12 may comprise base factors such as wire-frame data20 and/orterrain data24. For example, thereal façade texture16 of thebase image19 may be applied to the wire-frame of thestructure14. Thesystem10 may automatically rotate, stretch, or shrink thereal façade texture16 to align with edges of the wire-frame data20. Additionally, thesystem10 may provide for user evaluation and/or manipulation of thereal façade texture16.

Alternatively, wire-frame data20 and/orterrain data24 may provide a coordinate system for the three-dimensional model12 such that thereal façade texture16 is geographically positioned within the three-dimensional model according to the corresponding coordinates of the wire-frame data20 and/orterrain data24. Additionally, thereal façade texture16 may be applied to form the entire three-dimensional model12 or, alternatively, at least a portion of the three-dimensional model12.Multiple base images19 with multiplereal façade textures16 may form the three-dimensional model12.

In another embodiment, the real façade texture may be further processed to correctocclusions70, as illustrated inFIGS. 7 and 8. Generally, it is difficult to provide thereal façade texture16 of thebase image19 of thestructure14 withoutocclusions70 such as overlapping structures, visual distortions, and/or the like. For example,FIG. 7 illustrates thereal façade texture16 blocked by an overlappingstructure71. This blocked overlappingstructure71 causes anocclusion70 within thereal façade texture16. Multiple geo-referencedimages18 may not be able to provide thereal façade texture16 without the blocked overlappingstructure71. Therefore, methods are provided to correct for theocclusion70 within thereal façade texture16.

To correct for theocclusion70 within thereal façade texture16, thebase image19 is analyzed to locate ageographical position72 of theocclusion70. For example, thegeographical position72 may be identified using boundaries (74a,74b,74c,74d. . . ). Although the boundaries74a-74dare illustrated as a rectangle, it will be appreciated by one skilled in the art, the boundaries74a-74dmay comprise a circle, square, triangle, or any fanciful shape. Additionally, an edge-detection algorithm may be used to identify the geographical position of theocclusion70.

Once thegeographical position72 of theocclusion70 is located, the geo-referencedimages18 of thestructure14 are analyzed to locate at least oneimage76 having an unoccluded image characteristic78. As illustrated inFIG. 7, the geo-referencedimages18 of thestructure14 correcting for theocclusion70 are not required to be the same view as thebase image19.

The unoccluded image characteristic is applied to thereal façade texture16 forming amosaic image80. For example, pixels of the unoccluded image characteristic78 may replace pixels of theocclusion70 of thereal façade texture16. Themosaic image80 may include severalunoccluded image characteristics78 in addition to thereal façade texture16 of thebase image19.

Storage of themosaic image80 may be problematic if the file size of themosaic image80 is extremely large. Thus, it may be beneficial to use an algorithm for storing themosaic image80. For example, a rectangular area of themosaic image80 can be extracted and all information outside of the rectangular space cropped and removed. However, the geo-referencing information of the area would still be maintained within themosaic image80.

Occlusions70 are not limited to blocked areas on thereal façade texture16 but can also include misalignment of thereal façade texture16 when applied to the three-dimensional model12 and/or undesirable background images within thereal façade texture16.Occlusions70, misalignments, and background images may be identified using pattern recognition, contrast, and/or the like. For example, pattern recognition technically can be used to analyze each pixel or a group of pixels to determine whether the pixel belongs to thereal façade texture16 or is part of theocclusion70. The three-dimensional geometry of the surrounding buildings may also be a key factor.

Additionally, thereal façade texture16 may be optimized for depth complexity. Methods for optimizing depth complexity involve thesystem10 first determining whether overlapping elements within thereal façade texture16 areocclusions70 or desirable features of thereal façade texture16. If thesystem10 determines the overlapping elements are desirable features of thereal façade texture16, thesystem10 applies thereal façade texture16 of the overlapping structures to the three-dimensional model. For example, thesystem10 may detect a small roof structure that is overlapping a large roof structure. Thesystem10 will assume that the small roof structure is an element on top of the large roof structure and considered desirably within thereal façade texture16. The system will apply thereal façade texture16 of the overlapping structures to the three-dimensional model12. Depth complexity analyses the geometry of overlapping 3D structures, such as a small room on a large roof. Usually, walls are represented by vertical rectangles, from the top of the roof to the terrain. In this case, walls of the small room are created only to the large roof and not to the terrain.

The formation of the three-dimensional model12 withreal façade textures16 may be a continuous or intermittent process. Preferably, the formation of the three-dimensional model12 is automatically performed by thesystem10 to facilitate rapid modeling of an area. Using the methods as described herein, thesystem10 determines the geographic location of an area of interest and retrieves the appropriate wire-frame data20 and/orterrain data24 associated with the area. Thesystem10 automatically locates and identifiesstructures14 within the area based upon the wire-frame data20 and/orterrain data24 provided. Geo-referencedimages18 of the area are located by thesystem10 using the wire-frame data20 and/orterrain data24. The baseoblique image19 of thestructure14 is automatically selected by thesystem10 based on the image raster content of each of the geo-referencedimages18. If the baseoblique image19 contains more than onestructure14, thesystem10 may locate eachreal façade texture16 independently or together. Once thereal façade texture16 is located, thesystem10 may fix any occlusions if necessary and apply the real façade texture to the three-dimensional model12.

Generally, thesystem10 is a computer system that is able to embody and/or execute the logic of the processes described herein. The logic embodied may be executed on any appropriate hardware such as, for example, a dedicated system or systems, personal computer system, distributed processing computer system, and/or the like.

Referring now toFIG. 9, thesystem10 is preferably distributed, and includes ahost system112, communicating with one or more user devices114 via anetwork116. Thenetwork116 can be the Internet or other network. In either case, thehost system112 typically includes one ormore servers118 configured to communicate with thenetwork116 via one ormore gateways120. When thenetwork116 is the Internet, the primary user interface of thesystem10 is delivered through a series of web pages, but the primary user interface can be replaced by another type of interface, such as a Windows-based application. This method is also used when deploying thesystem10 in a stand-alone environment, such as a kiosk.

Thenetwork116 can be almost any type of network, although Internet and Internet2 networks are preferred because of the wide support of their underlying technologies. One embodiment of thenetwork116 exists in an Internet environment, which means a TCP/IP-based network. It is conceivable that in the near future, the preferred or other embodiments, may wish to use more advanced networking topologies.

Theservers118 can be networked with aLAN130. Thegateway120 is an entity responsible for providing access between theLAN130 and thenetwork116. Thegateway120 can also be used as a security means to protect theLAN130 from attack from external networks such as thenetwork116.

TheLAN130 network can be based on TCP/IP network such as the Internet, or it can based on another underlying network transport technology. The preferred embodiment uses an Ethernet network with TCP/IP because of the availability and acceptance of underlying technologies, but other embodiments may use other types of networks such as Fibre Channel, SCSI, Gigabit Ethernet, etc.

As discussed above, in one embodiment, thehost system112 includes theservers118. The configuration of the server hardware will depend upon the requirements and needs of the particular embodiment of thesystem10. Typical embodiments, including the preferred embodiment, will includemultiple servers118 with load balancing to increase stability and availability. It is envisioned that theservers118 will include database servers and application/web servers. The database servers are preferably separated from the application/web servers to improve availability and to provide the database servers with improved hardware and storage.

The user devices114 can be any number and type of device. Generally, user devices114 involve a user32, using a computer34 with a display36, keyboard38, and mouse40. It is contemplated user devices114 may include a touch screen element on the display in addition to or in lieu of the keyboard38 and/or mouse40.

Typically, the user device114 uses a type of software called a “browser” as indicated by reference numeral42 to render HTML/XHTML content that is generated when requesting resources from a source, such as thehost system112. In the preferred embodiment, thesystem10 is designed to be compatible with major Web Browser vendors (Microsoft Internet Explorer, Netscape Navigator, and Opera). Other embodiments may wish to focus on one particular browser depending upon the common user base using thesystem10. It should be noted, user devices114 may interact with thesystem10 through any suitable functional software, such as a program specifically designed for the individual embodiments of thesystem10.

The user devices114 can also be implemented as a portable device such as a laptop computer150 (or handheld computer); acellular telephone152 with a micro or embedded Web Browser; a Portable Digital Assistant154 (PDA) capable of wireless network access; a pen-based ortablet computer156, and/or the like. In another embodiment, the user device114 may be a cable box60 or other similar device for viewing through a display62 or television. Current embodiments of thesystem10 can also be modified to use any of these or similar future developed devices.

Thesystem10 is designed to provide flexibility in its deployment. Depending upon the requirements of the particular embodiment, the engine may be designed to work in almost any environment such as a desktop application, a web application, a series of web services designed to communicate with an external application, and/or the like.

The hardware and system software are designed with two key concerns: flexibility and scalability. Although some specifics for software and hardware components are described herein, it will be understood that a wide array of different components may be substituted. For example, different database vendors may be used, SML-based document stores may be used, and/or the like.

When thesystem10 is used to execute the logic of the processes described herein, such computer(s) and/or execution may be conducted at a same geographical location or multiple geographic locations. Furthermore, the execution of the logic may be conducted continuously or at multiple discrete times.

Thesystem10 includes one or more computer readable medium storing instructions for displaying a pixel representation of one or more of the images described herein including the geo-referencedimages18, thebase oblique images19,wire frame data20,terrain data24, the three-dimensional model12, and the like. The computer readable medium may be part of thehost system112, the user devices114, or combination thereof. Additionally, thesystem10 uses one or more databases orservers118 to store the images in an organized format. For example, the geo-referencedimages18 of thestructure14 may be sorted and stored by the direction showing the particularreal façade texture16.

Thesystem10 may also include instructions for (1) displaying pixel representations of the images as described above; (2) selecting the geographical location of interest; (3) altering and/or editing images; and (4) other similar tasks. The instructions typically run on a combination of the user devices114 and thehost system112.

Although the foregoing invention has been described in some detail by way of illustration and example for purposes of clarity of understanding, it will be obvious to those skilled in the art that certain changes and modifications may be practiced without departing from the spirit and scope thereof, as described in this specification and as defined in the appended claims below.

Claims (20)

What is claimed is:

1. A computer system for automatically generating a three-dimensional model, comprising:

hardware;

one or more computer server storing geo-referenced oblique images; and

one or more non-transitory computer readable medium accessible by the hardware and storing instructions that when executed by the hardware cause the hardware to:

obtain wire-frame data of a structure having a roof within a geographical area;

identify a geographic location of the roof of the structure within the geographical area;

retrieve from the one or more computer server multiple geo-referenced oblique images representing the geographic location and containing one or more real façade texture of the roof of the structure;

locate a geographical position of one or more real façade texture of the roof of the structure;

select one or more base oblique image from the multiple geo-referenced oblique images by analyzing, with selection logic, image raster content of the real façade texture depicted in the multiple geo-referenced oblique images, the selection logic using a factorial analysis of the image raster content; and,

apply the real façade texture of the one or more base oblique image to the wire-frame data of the structure to create a three-dimensional model providing a real-life representation of physical characteristics of the roof of the structure.

2. The computer system ofclaim 1, wherein locating a geographical position of one or more real façade texture of the roof of the structure comprises locating the geographical position of at least one real façade texture of the roof of the structure utilizing the wire-frame data.

3. The computer system ofclaim 1, wherein locating a geographical position of one or more real façade texture of the roof of the structure comprises locating the geographical position of at least one real façade texture of the roof of the structure utilizing terrain data.

4. The computer system ofclaim 1, wherein the factorial analysis is a weighted determination based on at least two factors, the factors including at least one of resolution of the oblique images, colour depth of the oblique images, proportional size of the real façade texture of the oblique images, contrast in the oblique images, time of day the oblique images were captured, time of year the oblique images were captured, amount of foliage in the oblique images, and contrast in lighting conditions in the oblique images.

5. The computer system ofclaim 1, wherein the one or more non-transitory computer readable medium stores instructions that when executed by the hardware further causes the hardware to:

analyze the real façade texture depicted within the base oblique image to locate a geographical position of at least one occlusion;

locate at least one oblique image having an unoccluded image characteristic of the occlusion in the real façade texture from the multiple oblique images; and,

apply the unoccluded image characteristic to the real façade texture forming a mosaic image.

6. The computer system ofclaim 5, wherein the instructions are configured to use pixel pattern recognition of the real façade texture to locate the occlusion.

7. The computer system ofclaim 5, wherein the oblique images are geo-referenced solved oblique images.

8. The computer system ofclaim 5, wherein the instructions are configured to remove the occlusion from the real façade texture.

9. The computer system ofclaim 1, further comprising instructions that when executed by the hardware cause the hardware to extract the real façade texture from the base oblique image, the real façade texture having geo-referenced information.

10. The computer system ofclaim 1, wherein the real façade texture includes overlapping structures having a geometry, and wherein the instructions, when executed by the hardware cause the hardware to analyze the geometry of the overlapping structures to determine whether the overlapping structures are occlusions or desirable features of the real façade texture.

11. The computer system ofclaim 10, wherein a first overlapping structure of the overlapping structures is a roof structure.

12. The computer system ofclaim 10, wherein the one or more non-transitory computer readable medium stores instructions that when executed by the hardware further causes the hardware to:

apply the real façade texture of the overlapping structures that are determined to be desirable features to the three-dimensional model.

13. A method for automatically generating a three-dimensional model, comprising:

obtaining, using one or more computer processor, wire-frame data of at least one structure having a roof;

identifying, using the one or more computer processor, a geographic location of the roof of the structure;

retrieving, from one or more computer server, multiple geo-referenced oblique images representing the geographic location and containing one or more real façade texture of the roof of the structure;

locating, using the one or more computer processor, a geographical position of one or more real façade texture of the roof of the structure;

selecting, using the one or more computer processor, one or more base oblique image from the multiple geo-referenced oblique images by analyzing, with selection logic, image raster content of the real façade texture depicted in the multiple oblique images, the selection logic using a factorial analysis of the image raster content; and,

applying, using the one or more computer processor, the real façade texture of the one or more base oblique image to the wire-frame data of the structure to create a three-dimensional model providing a real-life representation of physical characteristics of the roof of the structure.

14. The method ofclaim 13, wherein locating a geographical position of one or more real façade texture of the structure comprises locating the geographical position of at least one real façade texture of the roof of the structure utilizing the wire-frame data.

15. The method ofclaim 13, wherein locating a geographical position of one or more real façade texture of the roof of the structure comprises locating the geographical position of at least one real façade texture of the structure utilizing terrain data.

16. The method ofclaim 13, wherein the factorial analysis is a weighted determination based on at least two factors, the factors including at least one of resolution of the oblique images, colour depth of the oblique images, proportional size of the real façade texture of the oblique images, contrast in the oblique images, time of day the oblique images were captured, time of year the oblique images were captured, amount of foliage in the oblique images, and contrast in lighting conditions in the oblique images.

17. The method ofclaim 13, further comprising:

analyzing, using the one or more computer processor, the real façade texture depicted within the base oblique image to locate a geographical position of at least one occlusion;

locating, using the one or more computer processor, at least one oblique image having an unoccluded image characteristic of the occlusion in the real façade texture from the multiple oblique images; and,

applying, using the one or more computer processor, the unoccluded image characteristic to the real façade texture forming a mosaic image.

18. The method ofclaim 17, further comprising removing, using the one or more computer processor, the occlusion from the real façade texture.

19. The method ofclaim 13, wherein the real façade texture includes overlapping structures having a geometry, and further comprising, analyzing, using the one or more computer processor, the geometry of the overlapping structures to determine whether the overlapping structures are occlusions or desirable features of the real façade texture.

20. The method ofclaim 19, further comprising:

applying, using the one or more computer processor, the real façade texture of the overlapping structures that are determined to be desirable features to the three-dimensional model.

Images